BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260726T140512EDT-2570vc8nVv@132.216.98.100
DTSTAMP:20260726T180512Z
DESCRIPTION:Virtual Informal Systems Seminar (VISS) Centre for Intelligent 
 Machines (CIM) and Groupe d'Etudes et de Recherche en Analyse des Decision
 s (GERAD)\n\nAbhishek Gupta\n	Electrical and Computer Engineering \,  The O
 hio State University\n\nAbstract:\n\nMany stochastic optimization and empi
 rical dynamic programming algorithms have been proposed in the literature 
 that approximates certain deterministic algorithms. Examples of such algor
 ithms are stochastic gradient descent and empirical value iteration\, empi
 rical Q value iteration\, etc. for discounted or average cost MDPs. We ref
 er to them as stochastic recursive algorithms\, in which an exact contract
 ion operator is replaced with an approximate random operator at every step
  of the iteration. These algorithms can be viewed within the framework of 
 iterated random maps\, and thus Markov chain theory can be leveraged to st
 udy the convergence properties of these algorithms. In the talk\, we will 
 discover some new insights about the convergence properties of stochastic 
 recursive algorithms over infinite dimensional spaces. We will also presen
 t applications to some reinforcement learning algorithms\n\nBio:\n\nAbhish
 ek Gupta is an assistant professor in the ECE department at The Ohio State
  University. He completed his PhD in Aerospace Engineering from UIUC in 20
 14. His research interests are in stochastic control theory\, probability 
 theory\, and game theory with applications to transportation markets\, ele
 ctricity markets\, and cybersecurity of control systems.\n
DTSTART:20201002T150000Z
DTEND:20201002T160000Z
LOCATION:CA\, Zoom
SUMMARY:Stochastic Recursive Algorithms: A Markov Chain Perspective
URL:https://www.mcgill.ca/cim/channels/event/stochastic-recursive-algorithm
 s-markov-chain-perspective-325034
END:VEVENT
END:VCALENDAR